2021/05/18 by Dave Cliff, Cliff, Dave
Economics, Econometrics and Finance · Psychology · Social Sciences · #Artificial Intelligence in Law #Computational Engineering #Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Finance #Gambling Behavior and Treatments #Machine Learning (stat.ML) #Multiagent Systems (cs.MA) #Sports Analytics and Performance #Trading and Market Microstructure (q-fin.TR) #and Science (cs.CE)
paper · pdf · doi:10.48550/arxiv.2105.08310
openalex publication_date 2021/05/18 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
I describe the rationale for, and design of, an agent-based simulation model\nof a contemporary online sports-betting exchange: such exchanges, closely\nrelated to the exchange mechanisms at the heart of major financial markets,\nhave revolutionized the gambling industry in the past 20 years, but gathering\nsufficiently large quantities of rich and temporally high-resolution data from\nreal exchanges - i.e., the sort of data that is needed in large quantities for\nDeep Learning - is often very expensive, and sometimes simply impossible; this\ncreates a need for a plausibly realistic synthetic data generator, which is\nwhat this simulation now provides. The simulator, named the "Bristol Betting\nExchange" (BBE), is intended as a common platform, a data-source and\nexperimental test-bed, for researchers studying the application of AI and\nmachine learning (ML) techniques to issues arising in betting exchanges; and,\nas far as I have been able to determine, BBE is the first of its kind: a free\nopen-source agent-based simulation model consisting not only of a\nsports-betting exchange, but also a minimal simulation model of racetrack\nsporting events (e.g., horse-races or car-races) about which bets may be made,\nand a population of simulated bettors who each form their own private\nevaluation of odds and place bets on the exchange before and - crucially -\nduring the race itself (i.e., so-called "in-play" betting) and whose betting\nopinions change second-by-second as each race event unfolds. BBE is offered as\na proof-of-concept system that enables the generation of large high-resolution\ndata-sets for automated discovery or improvement of profitable strategies for\nbetting on sporting events via the application of AI/ML and advanced data\nanalytics techniques. This paper offers an extensive survey of relevant\nliterature and explains the motivation and design of BBE, and presents brief\nillustrative results.\n